We propose a method to learn 3D deformable object categories from raw
single-view images, without external supervision. The method is based on an
autoencoder that factors each input image into depth, albedo, viewpoint and
illumination. In order to disentangle these components without supervision, we
use the fact that many object categories have, at least in principle, a
symmetric structure. We show that reasoning about illumination allows us to
exploit the underlying object symmetry even if the appearance is not symmetric
due to shading. Furthermore, we model objects that are probably, but not
certainly, symmetric by predicting a symmetry probability map, learned
end-to-end with the other components of the model. Our experiments show that
this method can recover very accurately the 3D shape of human faces, cat faces
and cars from single-view images, without any supervision or a prior shape
model. On benchmarks, we demonstrate superior accuracy compared to another
method that uses supervision at the level of 2D image correspondences.

本文提出了一种无需外部监督学习从单视角图像中学习三维可变形物体类别的方法，该方法基于自编码器，将每个输入图像分解为深度、漫反射、观察角度和光照，通过利用物体对称结构来分解这些组件，推理光照使我们能够利用底层的物体对称性，即使外观不对称，而是由于阴影造成的。此外，我们通过预测对称概率地图来建模可能但不一定对称的对象，该地图与模型的其他组件一起端到端地学习。我们的实验表明，这种方法可以从单视角图像中非常准确地恢复人类脸部、猫脸和汽车的三维形状，而不需要任何监督或先前的形状模型。与使用 2D 图像对应的监督方法相比，在基准测试中，我们表现出优越的准确性。